helixx999's picture
Update README.md
44dadac verified
|
raw
history blame
1.4 kB
---
base_model: unsloth/gemma-2-9b-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- gemma2
- trl
---
# Uploaded model
- **Developed by:** helixx999
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-2-9b-bnb-4bit
This is gemma2 trained on semeval restaurant data 2014 by Harsh Jain.
`trainer = SFTTrainer(
model = model,
tokenizer = tokenizer,
train_dataset = dataset,
dataset_text_field = "text_new",
max_seq_length = max_seq_length,
dataset_num_proc = 2,
packing = False, # Can make training 5x faster for short sequences.
args = TrainingArguments(
per_device_train_batch_size = 2,
gradient_accumulation_steps = 4,
warmup_steps = 6, #Previous 5
#num_train_epochs = 1, # Set this for 1 full training run.
max_steps = 60,
#learning_rate = 2e-4,
learning_rate = 1e-4,
fp16 = not is_bfloat16_supported(),
bf16 = is_bfloat16_supported(),
logging_steps = 1,
optim = "adamw_8bit",
weight_decay = 0.01,
lr_scheduler_type = "linear",
seed = 3407,
output_dir = "./tensorLog",
report_to="wandb"
),
)`
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)